Pureframe AI API Documentation

You are helping a user connect their AI coding tool or agent to the Pureframe AI MCP server. It gives you tools to search, list, and manage the user’s indexed videos: search_videos, list_collections, get_collection, get_video, get_job_status, upload_video.

1. Identify which client you are

Determine which of these you’re running as, then jump to its config below. If you can’t tell, ask the user.

Claude Code
Claude Desktop
Cursor
VS Code (GitHub Copilot, Agent mode)
Codex
OpenCode

2. Get an API key

The user needs a Pureframe AI API key (pf_...). Keys can only be created from a signed-in browser session. Direct the user to https://platform.pureframe.ai/settings/api-keys and recommend a read_only key for search and list operations. Do not ask the user to paste the key into chat. Ask them to set it in the client configuration or a local environment variable. Use a placeholder such as pf_... in any configuration you generate.

3. Add the MCP server config

All clients run the same local server via npx -y @pureframeai/mcp, configured with one environment variable: PUREFRAME_API_KEY. Claude Code: run:

claude mcp add pureframe -- npx -y @pureframeai/mcp

Then ask the user to set PUREFRAME_API_KEY in their environment, or add it manually to ~/.claude.json:

{
  "mcpServers": {
    "pureframe": {
      "command": "npx",
      "args": ["-y", "@pureframeai/mcp"],
      "env": { "PUREFRAME_API_KEY": "pf_..." }
    }
  }
}

Claude Desktop: add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "pureframe": {
      "command": "npx",
      "args": ["-y", "@pureframeai/mcp"],
      "env": { "PUREFRAME_API_KEY": "pf_..." }
    }
  }
}

Cursor: add to .cursor/mcp.json:

{
  "mcpServers": {
    "pureframe": {
      "command": "npx",
      "args": ["-y", "@pureframeai/mcp"],
      "env": { "PUREFRAME_API_KEY": "pf_..." }
    }
  }
}

VS Code: add to .vscode/mcp.json. Note the root key is servers, not mcpServers:

{
  "servers": {
    "pureframe": {
      "command": "npx",
      "args": ["-y", "@pureframeai/mcp"],
      "env": { "PUREFRAME_API_KEY": "pf_..." }
    }
  }
}

Open Copilot Chat and switch to Agent mode to use it. Codex: add to ~/.codex/config.toml:

[mcp_servers.pureframe]
command = "npx"
args = ["-y", "@pureframeai/mcp"]

[mcp_servers.pureframe.env]
PUREFRAME_API_KEY = "pf_..."

OpenCode: add to opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pureframe": {
      "type": "local",
      "command": ["npx", "-y", "@pureframeai/mcp"],
      "environment": { "PUREFRAME_API_KEY": "pf_..." }
    }
  }
}

4. Confirm

Restart or reload the client if needed, then confirm the connection by making a sample tool call: e.g. search the user’s videos for something they mention, or list their collections. Full per-client reference: https://docs.pureframe.ai/agents/connect-an-agent

Get Started

Search

Video Processing

Agents

Production

Resources

Agent Setup

1. Identify which client you are

2. Get an API key

3. Add the MCP server config

4. Confirm

​1. Identify which client you are

​2. Get an API key

​3. Add the MCP server config

​4. Confirm

1. Identify which client you are

2. Get an API key

3. Add the MCP server config

4. Confirm